© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2694
    Prev
    Next
    INDEX
    Explanations

    Court names, locations, programming terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zigen
    -0.77
    SEB
    -0.72
     dez
    -0.71
     عزیزم
    -0.70
    革命
    -0.69
    ByPrimaryKey
    -0.68
     Phoebe
    -0.68
    SPM
    -0.68
     Dez
    -0.68
    숭
    -0.67
    POSITIVE LOGITS
     만화
    0.73
     personalise
    0.70
     coiled
    0.69
    english
    0.69
     Mobile
    0.68
    stva
    0.68
    itates
    0.68
    cipl
    0.68
    ggak
    0.67
     Hypers
    0.67
    Activations Density 0.021%

    No Known Activations